Weber Local Descriptor based object recognition

Recognizing the objects seems to be the challenging task as the object may be occluded, may vary in shape and position and in size. The proposed method is to recognize objects based on the computation of Weber Local Descriptor as feature to the image patches which are extracted around the salient points over the image in order to represent the local properties of the image. Weber Local Descriptor is applied to the Image Patches in order to extract the Salient features. WLD consists of two parts, one is Differential Excitation and the other is Orientation by which the local salient features are extracted. Then these features are fed to SVM classifier. Benchmark database used here is UIUC database. Experimental results by varying the patch sizes are given and the results obtained are satisfactory.